Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3506 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.5320. Min Act: -0.0000

Data Index: 727400 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3913. Min Act: -0.0000

Data Index: 213204 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1348624 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1048193 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3871. Min Act: -0.0000

Data Index: 898665 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3802. Min Act: -0.0000

Data Index: 860963 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3389. Min Act: -0.0000

Data Index: 272601 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3355. Min Act: -0.0000

Data Index: 728850 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3351. Min Act: -0.0000

Data Index: 328402 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3613. Min Act: -0.0000

Data Index: 723423 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3346. Min Act: -0.0000

Data Index: 99253 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3082. Min Act: -0.0000

Data Index: 819940 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1033370 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3199. Min Act: -0.0000

Data Index: 141485 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3274. Min Act: -0.0000

Data Index: 699778 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3031. Min Act: -0.0000

Data Index: 992062 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3192. Min Act: -0.0000

Data Index: 625871 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3093. Min Act: -0.0000

Data Index: 855564 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3100. Min Act: -0.0000

Data Index: 718659 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.5320. Min Range: -0.5320

Max Act: 0.3129. Min Act: 0.0001

Data Index: 1298341 (C4 (Web Text))

Max Activating Token Index: 323